Glossary

Definitions of the key terms used throughout Lip Dubber, listed alphabetically.

Audio separation: The stage that splits spoken vocals from background music or other sounds so later stages can work with cleaner speech.
Credits: The usage balance tied to your account and subscription. Credits are consumed when you process dubbing jobs.
Dubbing job: A single processing request for one uploaded media file, including its selected language, voice, and pipeline settings.
Dubbing pipeline: The ordered set of stages that process your media, such as audio separation, transcription, translation, text-to-speech, lip sync, and rendering.
Lip sync: The process of adjusting mouth movement in the video so it matches the newly generated spoken audio.
Presets: Saved pipeline configurations that let you quickly reuse the same setup for future dubbing jobs.
Rendering: The final stage that combines the processed video and audio into the finished output file you can preview or download.
Source language: The language spoken in the original media before translation.
Target language: The language you want the final dubbed output to use.
Text-to-speech (TTS): The stage that turns translated text into synthetic speech using the selected voice and model.
Transcription: The stage that converts spoken audio from the original media into text.
Translation: The stage that converts transcribed text from the source language into the target language.
Video dubbing: Replacing or recreating the spoken audio in a video in another language while preserving meaning, timing, and presentation.
Voice settings: The options that control which synthetic voice is used and, depending on the engine, how that generated speech should sound.